Tech
Drone Flies Autonomously and Learns New Routes Using Navigation System
Catherine Griffin
First Posted: May 26, 2015 10:37 AM EDT
Drones may be getting a bit smarter. Scientists have created a new vision and learning system that allow drones to learn a control themselves without relying on a GPS signal or trained personnel.
The main idea for the new system was to avoid the use of GPS. Instead, researchers opted for the use of video cameras on board of the vehicle for visual information. They then applied an algorithm to locate and orient the drone during its flight to use this visual information. More specifically, the drone has a function that allows it to draw a specific route on a map using an aerial view.
"At the stage of repeating, the pilot just makes the drone take off, but once in the air, autonomous flight algorithms kick into action and, by processing visual information captured by the camera, the vehicle recognizes where in the environment it is positioned," said Jose Martinez, the lead researchers, in a news release.
Once the drone recognizes its location, visual information estimates vehicle position. This is sent to the control algorithms, which are responsible for moving the drone. The drone then navigates to each of the points made in the route recorded during the stage teaching.
The new system is useful for drone navigation and is just another step forward when it comes to refining these flying robots. In the future, the drone may be capable of being operated from wearable devices and could be used for surveillance, exploration of properties in the inspection of towers, and other applications.
For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).
See Now:
NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone
TagsDrone ©2024 ScienceWorldReport.com All rights reserved. Do not reproduce without permission. The window to the world of science news.
More on SCIENCEwr
First Posted: May 26, 2015 10:37 AM EDT
Drones may be getting a bit smarter. Scientists have created a new vision and learning system that allow drones to learn a control themselves without relying on a GPS signal or trained personnel.
The main idea for the new system was to avoid the use of GPS. Instead, researchers opted for the use of video cameras on board of the vehicle for visual information. They then applied an algorithm to locate and orient the drone during its flight to use this visual information. More specifically, the drone has a function that allows it to draw a specific route on a map using an aerial view.
"At the stage of repeating, the pilot just makes the drone take off, but once in the air, autonomous flight algorithms kick into action and, by processing visual information captured by the camera, the vehicle recognizes where in the environment it is positioned," said Jose Martinez, the lead researchers, in a news release.
Once the drone recognizes its location, visual information estimates vehicle position. This is sent to the control algorithms, which are responsible for moving the drone. The drone then navigates to each of the points made in the route recorded during the stage teaching.
The new system is useful for drone navigation and is just another step forward when it comes to refining these flying robots. In the future, the drone may be capable of being operated from wearable devices and could be used for surveillance, exploration of properties in the inspection of towers, and other applications.
For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).
See Now: NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone